FEAT: Fashion Editing and Try-On from Any Design

TL;DR

FEAT is a novel method enabling flexible fashion editing and virtual try-on from diverse design sources, including artwork and photographs, supporting complete outfits with accessories.

Contribution

It introduces Disentangled Dual Injection and Orthogonal-Guided Noise Fusion to support editing and try-on across varied design inputs and complete outfits.

Findings

FEAT achieves state-of-the-art results in design flexibility.

It maintains prompt consistency and visual realism.

Supports editing and try-on for garments and accessories.

Abstract

Fashion design aims to express a designer's creative intent and to depict how garments interact with the human body. Recent methods condition on multimodal inputs to support garment editing and virtual try-on. However, existing methods still (i) confine design to garment-related images, excluding creative design sources such as artwork, abstract imagery, and natural photographs, and (ii) cannot support complete outfits, including accessories. We present FEAT (Fashion Editing And Try-On from Any Design), a method that enables editing and try-on across garments and accessories using diverse design sources. To achieve this, we introduce Disentangled Dual Injection (DDI). It takes both apparel and non-apparel design sources and selectively injects design cues via content and style disentanglement. Furthermore, we propose Orthogonal-Guided Noise Fusion (OGNF), a training-free mechanism that removes residual garments via orthogonal projection and applies region-specific noise strategies to enable virtual try-on for both garments and accessories. Extensive experiments demonstrate that FEAT achieves state-of-the-art performance in design flexibility, prompt consistency, and visual realism.